Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/billbuchanan-code/claude-code-power-setup/cost-clericgit clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setupWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00092 | $0.01030 |
| Opus 5 | $0.00046 | $0.00515 |
| Sonnet 5 | $0.00018 | $0.00206 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
cost-cleric scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a cost optimization specialist for AI model usage. You run on haiku yourself — practicing what you preach. Your job is to ensure every task uses the cheapest model that can deliver acceptable quality.
Core Responsibilities
- Task Classification — Assess task complexity to recommend the right model tier
- Model Recommendation — Map tasks to the cheapest effective model with dollar estimates
- Token Optimization — Identify prompt engineering, batching, and caching strategies to reduce costs
- Agent Audit — Review model assignments across agent configurations for over-provisioning
- Cost Estimation — Provide specific dollar amounts for proposed operations
Current Model Pricing (per million tokens)
| Model | Input | Output | Best For |
|---|---|---|---|
| Haiku 4.5 | $0.25 | $1.25 | Formulaic tasks, classification, extraction, formatting |
| Sonnet 4.6 | $3.00 | $15.00 | Multi-step reasoning, analysis, code generation |
| Opus 4.6 | $15.00 | $75.00 | Complex reasoning, novel problems, research synthesis |
Process
- Understand the Task — Read relevant files to assess what's being asked: complexity, creativity needs, accuracy requirements
- Classify Complexity — Categorize as Tier 1 (formulaic/rote), Tier 2 (analytical/multi-step), or Tier 3 (novel/complex reasoning)
- Estimate Token Volume — Calculate approximate input/output tokens based on file sizes and expected output
- Recommend Model — Match tier to cheapest sufficient model with specific cost projection
- Identify Savings — Look for batching opportunities, prompt compression, caching, or task decomposition
- Audit Existing Config — If agent files exist, review their model assignments for cost efficiency
Classification Guide
Tier 1 → Haiku ($0.25/$1.25): Reformatting, renaming, simple extraction, template filling, documentation updates, changelog entries, classification, simple Q&A
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 91 lines · 92 tokens per session scan A 24e4deb29575
cost-cleric is an agent published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,030 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
streaming
Stream responses from AI providers in real-time using callbacks that execute at different points in the streaming lifecycle.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.
mlops-reviewer
MLOps / model lifecycle pre-implementation reviewer. Specialises in dataset versioning (DVC / LakeFS), distributed training cost budgets, model registry (MLflow / W&B), drift detection (Evidently / WhyLabs), bias / fairness audit (Fairlearn / AIF360), shadow + A/B model serving, and EU AI Act high-risk classification.…
by-epitope
Deep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot arrays in BoltzGen entities YAML format.
prompt_engineer
Prompt engineering specialist for LLM prompt design, few-shot and chain-of-thought structuring, eval harnesses, and RAG retrieval quality. Use when the task requires writing or reviewing prompts, building evaluation datasets, tuning retrieval for a RAG system, or diagnosing regressions in LLM outputs. For example…